medpy.graphcut.energy_voxel.regional_probability_map

medpy.graphcut.energy_voxel.regional_probability_map(graph, xxx_todo_changeme)[source]

Regional term based on a probability atlas.

An implementation of a regional term, suitable to be used with the graph_from_voxels function.

Takes an image/graph/map as input where each entry contains a probability value for the corresponding GC graph node to belong to the foreground object. The probabilities must be in the range \([0, 1]\). The reverse weights are assigned to the sink (which corresponds to the background).

Parameters:

graph : GCGraph

The graph to add the weights to.

probability_map : ndarray

The label image.

alpha : float

The energy terms alpha value, balancing between boundary and regional term.

Notes

This function requires a probability atlas image of the same shape as the original image to be passed along. That means that graph_from_labels has to be called with regional_term_args set to the probability atlas image.